README.md

---
license: creativeml-openrail-m
datasets:
- SubMaroon/danbooru-colored
base_model:
- John6666/nsfw-anime-xl-v1-sdxl
tags:
- controlnet
- anime
- stable-diffusion-xl-diffusers
- text-to-image
- stable-diffusion-xl
---
# ControlNet for Manga Colorization

**Model Name:** `SubMaroon/ControlNet-manga-recolor`  
**Base model:** `John6666/nsfw-anime-xl-v1-sdxl`  
**Task:** Conditional image generation — Colorization  
**Conditioning:** Grayscale manga panel (lineart or filled)  
**Trained with:** [Hugging Face diffusers](https://github.com/huggingface/diffusers) ControlNet training pipeline

---

## Description

This is a custom-trained **ControlNet** model designed to perform **automatic colorization of grayscale anime styled** images.

The model takes in a **black-and-white anime styled pictures** (converted to RGB) as conditioning input and generates a **colorized version** using Stable Diffusion.

It is trained to act as a ControlNet module and requires a compatible SDXL base model — such as `nsfw-anime-xl-v1-sdxl` or other anime/manga-focused SDXL models.

---

## Training details

- **Base model:** `John6666/nsfw-anime-xl-v1-sdxl`
- **Dataset:** Custom dataset of ~6,000 image pairs from **Danbooru-based manga scans**, manually cleaned and resized to `768x768`
- **Inputs:**
  - `conditioning_image`: black-and-white manga scan (RGB)
  - `text prompt`: optional (e.g. "1girl, blue_eyes, blue_hair etc.")
- **Loss:** MSE with FP16, trained on 1×RTX3090, 4 epochs
- **Resolution:** 768x768  
- **Scheduler:** default diffusers setup
- **Optimizer:** LR: `1.4e-4`

---

## Usage (Diffusers)

```python
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
from diffusers.utils import load_image
import torch

# Load ControlNet
controlnet = ControlNetModel.from_pretrained("SubMaroon/ControlNet-manga-recolor", torch_dtype=torch.float16)

# Load base pipeline
pipe = StableDiffusionControlNetPipeline.from_pretrained(
    "John6666/nsfw-anime-xl-v1-sdxl", controlnet=controlnet, torch_dtype=torch.float16
)

pipe.to("cuda")

# Load grayscale manga panel
conditioning_image = load_image("bw_manga_panel.png").convert("RGB")

# Generate
image = pipe("manga colorization", image=conditioning_image, num_inference_steps=30).images[0]
image.save("colorized.png")
```

---

## Usage in ComfyUI / WebUI

- Place `diffusion_pytorch_model.safetensors` into your `ComfyUI/models/controlnet/` folder
- Make sure to also include the `config.json`
- Select this ControlNet in your workflow
- Use grayscale images as conditioning inputs

---

## Alternative training run (SDXL version)

This version was trained using the SDXL-compatible ControlNet pipeline with the following CLI command:

```bash
accelerate launch train_controlnet.py \
  --pretrained_model_name_or_path="John6666/nsfw-anime-xl-v1-sdxl" \
  --dataset_name="SubMaroon/danbooru-colored" \
  --image_column="image" \
  --conditioning_image_column="conditioning_image" \
  --caption_column="prompt" \
  --output_dir="./controlnet-colorization" \
  --resolution=768 \
  --train_batch_size=4 \
  --gradient_accumulation_steps=4 \
  --learning_rate=1.4e-4 \
  --num_train_epochs=12 \
  --mixed_precision="fp16" \
  --gradient_checkpointing \
  --checkpointing_steps=1000 \
  --validation_steps=1000 \
  --report_to="tensorboard" \
  --tracker_project_name="controlnet-colorization" \
  --seed=42
```

---

## License

The model is released under the **CreativeML Open RAIL-M** license.  
You are free to use it for non-commercial and research purposes. Commercial use may require additional permission.

---

## Credits

Created by [SubMaroon](https://huggingface.co/SubMaroon)  
Trained with compute generously provided by [Flanayt Pulsar](https://huggingface.co/fisb)  
Based on the Hugging Face [`diffusers`](https://github.com/huggingface/diffusers) ControlNet training example  
Inspired by [lllyasviel's original ControlNet](https://github.com/lllyasviel/ControlNet)